© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 119620
    Prev
    Next
    INDEX
    Explanations

    countries and cities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     such
    -1.56
     by
    -1.48
     as
    -1.48
     the
    -1.48
     one
    -1.42
     السياس
    -1.41
     what
    -1.31
     increase
    -1.30
     large
    -1.27
     four
    -1.25
    POSITIVE LOGITS
     graines
    1.39
     trámite
    1.37
    Kelebihan
    1.28
     concurred
    1.28
     gouttes
    1.27
    Ꭵ
    1.27
     („
    1.25
    侂
    1.24
    小麦
    1.24
    اقتصاد
    1.24
    Activations Density 0.092%

    No Known Activations